Agent blueprint

How to build a research assistant

Free blueprint for a research assistant. A low-code, single-agent, cloud-hosted stack with 12 connected components. Built around Elicit, NotebookLM, Tavily, Firecrawl. Copy it, export it, or change the answers to fit your project.

Get the code
Your architecture

Research assistant

A low-code, single-agent, cloud-hosted stack with 12 connected components.

Sign in to save

Architecture map

Tap a component to see its connections

INTERFACE &TRIGGERSORCHESTRATIONREASONINGMEMORY &KNOWLEDGETOOLS &INTEGRATIONSMONITORING &SAFETYCHAT INTERFACEWeb chat widgetVISUAL AGENT CANVASFlowiseREASONING MODELGeminiCONVERSATION MEMORYBuilt into yourorchestratorDOCUMENT INGESTIONBuilt-in knowledgebaseVECTOR DATABASEPineconeWEB SEARCHTavilyBROWSING & SCRAPINGFirecrawlDOCS & WIKISNotionACADEMIC PAPERSElicitSOURCE NOTEBOOKNotebookLMTRACING & EVALUATIONLangfuse

Swipe sideways to see the whole map

Tool configuration

Interface & triggers

  • Chat interface

    Where people talk to the agent

    Web chat widget

    or Slack or Teams bot

Orchestration

  • Visual agent canvas

    Drag-and-drop agent loop you can extend

    Flowise

    or Langflow, Dify

Reasoning

  • Reasoning model

    Reads very long documents in one go

    Gemini

    or Claude, ChatGPT / OpenAI

Memory & knowledge

  • Conversation memory

    Keeps track of the current chat or task

    Built into your orchestrator
  • Document ingestion

    Splits and indexes your files and pages

    Built-in knowledge base

    or Firecrawl, LlamaIndex

  • Vector database

    Finds the most relevant passages for each question

    Pinecone

    or Weaviate, Qdrant

Tools & integrations

  • Web search

    Fetches fresh facts from the live web

    Tavily

    or Exa, Perplexity

  • Browsing & scraping

    Reads and acts on websites

    Firecrawl

    or Browse AI, Browserbase

  • Docs & wikis

    Reads and writes team documents

    Notion

    or Google Drive, Confluence

  • Academic papers

    Finds and summarises peer-reviewed research

    Elicit

    or Consensus, Scite

  • Source notebook

    Answers questions only from the sources you add

    NotebookLM

    or ChatPDF

Monitoring & safety

  • Tracing & evaluation

    Records every step, cost and answer quality

    Langfuse

    or LangSmith, Weights & Biases

Set up your agent, step by step

Tick each step as you finish it. Your progress is saved with this plan in your AItooling account.

0 of 19 done

AItooling never signs up for you and never asks for your passwords or keys. You create each account yourself on the tool's own website, and only your ticks are saved here.

Sign in and save this plan to keep your progress in your account.

  1. 1Create your accounts

    • Sign up or install it, then make a new project for this agent.

    • Sign up, create an API key and set a monthly spending limit before anything else.

    • Sign up and create a new database or index just for this agent.

    • Sign up and connect only the apps this agent needs, with read-only access where you can.

    • Sign up and connect only the apps this agent needs, with read-only access where you can.

    • Sign up and connect only the apps this agent needs, with read-only access where you can.

    • Sign up and connect only the apps this agent needs, with read-only access where you can.

    • Sign up and connect only the apps this agent needs, with read-only access where you can.

    • Sign up and turn on logging so you can review what the agent does.

  2. 2Build it in this order

  3. 3Launch your agent

    • Copy the ready-made code for this agent. It hides secrets and personal data before the AI model sees them.

    • Put each key in a password manager or your hosting's secret settings. Never paste keys or passwords into AItooling or a chat.

    • Start small, read every answer yourself, and only then let other people use it.

Want to go deeper?

Read our step-by-step guides on building agents. Browse guides

More AI agent blueprints